© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8858
    Prev
    Next
    INDEX
    Explanations

    converted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     conversion
    -0.55
     diffusion
    -0.53
     Conversion
    -0.46
     Convert
    -0.45
     Den
    -0.45
     Gray
    -0.44
     H
    -0.44
     Converting
    -0.43
    rowe
    -0.43
     converted
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.79
    providedIn
    0.71
    SourceChecksum
    0.70
     Seeder
    0.66
    లాలు
    0.65
    sidemargin
    0.65
    SharedDtor
    0.65
     Roskov
    0.63
     hâte
    0.61
    erializer
    0.60
    Activations Density 0.005%

    No Known Activations